Violence Detection System Model Using CCTV Cameras on Public
INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 20.03.2026 · 10 (03) · 1-9
DOI: 10.55041/ijsrem57976 ↗Kurz gefasst
Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 20.03.2026. Verfasst von T . Kowsalya und 4 weiteren Autor:innen.
Abstract (Originalsprache)
1. Abstract: From busy streets to crowded stations, fights caught on camera are pushing new ways to spot danger fast. Watching every screen by hand? That effort often misses things, slips through cracks. Instead, machines now scan footage, looking for sudden movements or clashes between people. Outcomes shift when software learns what yelling, shoving, or swinging looks like over time. Cameras feed into programs trained to flag chaos before it spreads unseen. From video clips, the model pulls out space and time patterns by linking convolutional networks with sequence-aware layers, helping it spot violence more reliably frame after frame. Instead of just stacking parts, attention mechanisms sharpen key signals while adjusted loss rules reduce errors caused by uneven data or messy backgrounds. Testing happens on standard security footage collections, measuring results via precision scores, curve area size, and equal error thresholds - each showing better outcomes than older methods. What stands out is how small shifts in weighting boost sensitivity without breaking stability under tough lighting or cluttered scenes. What helps boost results is adding attention layers that highlight key movement areas while downplaying unimportant surroundings.Testing happens on standard video monitoring collections, where success gets measured by numbers like Accuracy, AUC, Precision, Recall, F1-score, plus EER at their crossover point. Keywords: Violence Detection,CCTV Surveillance,Deep Learning,Computer Neural Network(CNN).
Zitieren
APA
Kowsalya, T., S, D., .M, K., kumar.U, M., & kumar.R, N. (2026). Violence Detection System Model Using CCTV Cameras on Public. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(03), 1-9. https://doi.org/10.55041/ijsrem57976
Vancouver
Kowsalya T, S D, .M K, kumar.U M, kumar.R N. Violence Detection System Model Using CCTV Cameras on Public. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(03):1-9. doi:10.55041/ijsrem57976
BibTeX
@article{Kowsalya2026,
author = {Kowsalya, T . and S, Duraimurugan. and .M, Karthikeyan and kumar.U, Mukesh and kumar.R, Nathish},
title = {Violence Detection System Model Using CCTV Cameras on Public},
journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
year = {2026},
volume = {10},
number = {03},
pages = {1--9},
doi = {10.55041/ijsrem57976}
}
EUVIMED